Personalized grade prediction: A data mining approach

Yannick Meier, Jie Xu, Onur Atan, Mihaela Van Der Schaar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

To increase efficacy in traditional classroom courses as well as in Massive Open Online Courses (MOOCs), automated systems supporting the instructor are needed. One important problem is to automatically detect students that are going to do poorly in a course early enough to be able to take remedial actions. This paper proposes an algorithm that predicts the final grade of each student in a class. It issues a prediction for each student individually, when the expected accuracy of the prediction is sufficient. The algorithm learns online what is the optimal prediction and time to issue a prediction based on past history of students' performance in a course. We derive demonstrate the performance of our algorithm on a dataset obtained based on the performance of approximately 700 undergraduate students who have taken an introductory digital signal processing over the past 7 years. Using data obtained from a pilot course, our methodology suggests that it is effective to perform early in-class assessments such as quizzes, which result in timely performance prediction for each student, thereby enabling timely interventions by the instructor (at the student or class level) when necessary.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Data Mining, ICDM
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages907-912
Number of pages6
Volume2016-January
ISBN (Print)9781467395038
DOIs
StatePublished - Jan 5 2016
Externally publishedYes
Event15th IEEE International Conference on Data Mining, ICDM 2015 - Atlantic City, United States
Duration: Nov 14 2015Nov 17 2015

Other

Other15th IEEE International Conference on Data Mining, ICDM 2015
CountryUnited States
CityAtlantic City
Period11/14/1511/17/15

Fingerprint

Data mining
Students
Digital signal processing

Keywords

  • Data mining
  • Digital signal processing education
  • Forecasting algorithms
  • Grade prediction
  • Online learning

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Meier, Y., Xu, J., Atan, O., & Van Der Schaar, M. (2016). Personalized grade prediction: A data mining approach. In Proceedings - IEEE International Conference on Data Mining, ICDM (Vol. 2016-January, pp. 907-912). [7373410] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDM.2015.54

Personalized grade prediction : A data mining approach. / Meier, Yannick; Xu, Jie; Atan, Onur; Van Der Schaar, Mihaela.

Proceedings - IEEE International Conference on Data Mining, ICDM. Vol. 2016-January Institute of Electrical and Electronics Engineers Inc., 2016. p. 907-912 7373410.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Meier, Y, Xu, J, Atan, O & Van Der Schaar, M 2016, Personalized grade prediction: A data mining approach. in Proceedings - IEEE International Conference on Data Mining, ICDM. vol. 2016-January, 7373410, Institute of Electrical and Electronics Engineers Inc., pp. 907-912, 15th IEEE International Conference on Data Mining, ICDM 2015, Atlantic City, United States, 11/14/15. https://doi.org/10.1109/ICDM.2015.54
Meier Y, Xu J, Atan O, Van Der Schaar M. Personalized grade prediction: A data mining approach. In Proceedings - IEEE International Conference on Data Mining, ICDM. Vol. 2016-January. Institute of Electrical and Electronics Engineers Inc. 2016. p. 907-912. 7373410 https://doi.org/10.1109/ICDM.2015.54
Meier, Yannick ; Xu, Jie ; Atan, Onur ; Van Der Schaar, Mihaela. / Personalized grade prediction : A data mining approach. Proceedings - IEEE International Conference on Data Mining, ICDM. Vol. 2016-January Institute of Electrical and Electronics Engineers Inc., 2016. pp. 907-912
@inproceedings{a2c4046b4b064a288d967d069dedb3a5,
title = "Personalized grade prediction: A data mining approach",
abstract = "To increase efficacy in traditional classroom courses as well as in Massive Open Online Courses (MOOCs), automated systems supporting the instructor are needed. One important problem is to automatically detect students that are going to do poorly in a course early enough to be able to take remedial actions. This paper proposes an algorithm that predicts the final grade of each student in a class. It issues a prediction for each student individually, when the expected accuracy of the prediction is sufficient. The algorithm learns online what is the optimal prediction and time to issue a prediction based on past history of students' performance in a course. We derive demonstrate the performance of our algorithm on a dataset obtained based on the performance of approximately 700 undergraduate students who have taken an introductory digital signal processing over the past 7 years. Using data obtained from a pilot course, our methodology suggests that it is effective to perform early in-class assessments such as quizzes, which result in timely performance prediction for each student, thereby enabling timely interventions by the instructor (at the student or class level) when necessary.",
keywords = "Data mining, Digital signal processing education, Forecasting algorithms, Grade prediction, Online learning",
author = "Yannick Meier and Jie Xu and Onur Atan and {Van Der Schaar}, Mihaela",
year = "2016",
month = "1",
day = "5",
doi = "10.1109/ICDM.2015.54",
language = "English (US)",
isbn = "9781467395038",
volume = "2016-January",
pages = "907--912",
booktitle = "Proceedings - IEEE International Conference on Data Mining, ICDM",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Personalized grade prediction

T2 - A data mining approach

AU - Meier, Yannick

AU - Xu, Jie

AU - Atan, Onur

AU - Van Der Schaar, Mihaela

PY - 2016/1/5

Y1 - 2016/1/5

N2 - To increase efficacy in traditional classroom courses as well as in Massive Open Online Courses (MOOCs), automated systems supporting the instructor are needed. One important problem is to automatically detect students that are going to do poorly in a course early enough to be able to take remedial actions. This paper proposes an algorithm that predicts the final grade of each student in a class. It issues a prediction for each student individually, when the expected accuracy of the prediction is sufficient. The algorithm learns online what is the optimal prediction and time to issue a prediction based on past history of students' performance in a course. We derive demonstrate the performance of our algorithm on a dataset obtained based on the performance of approximately 700 undergraduate students who have taken an introductory digital signal processing over the past 7 years. Using data obtained from a pilot course, our methodology suggests that it is effective to perform early in-class assessments such as quizzes, which result in timely performance prediction for each student, thereby enabling timely interventions by the instructor (at the student or class level) when necessary.

AB - To increase efficacy in traditional classroom courses as well as in Massive Open Online Courses (MOOCs), automated systems supporting the instructor are needed. One important problem is to automatically detect students that are going to do poorly in a course early enough to be able to take remedial actions. This paper proposes an algorithm that predicts the final grade of each student in a class. It issues a prediction for each student individually, when the expected accuracy of the prediction is sufficient. The algorithm learns online what is the optimal prediction and time to issue a prediction based on past history of students' performance in a course. We derive demonstrate the performance of our algorithm on a dataset obtained based on the performance of approximately 700 undergraduate students who have taken an introductory digital signal processing over the past 7 years. Using data obtained from a pilot course, our methodology suggests that it is effective to perform early in-class assessments such as quizzes, which result in timely performance prediction for each student, thereby enabling timely interventions by the instructor (at the student or class level) when necessary.

KW - Data mining

KW - Digital signal processing education

KW - Forecasting algorithms

KW - Grade prediction

KW - Online learning

UR - http://www.scopus.com/inward/record.url?scp=84963611408&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963611408&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2015.54

DO - 10.1109/ICDM.2015.54

M3 - Conference contribution

AN - SCOPUS:84963611408

SN - 9781467395038

VL - 2016-January

SP - 907

EP - 912

BT - Proceedings - IEEE International Conference on Data Mining, ICDM

PB - Institute of Electrical and Electronics Engineers Inc.

ER -